© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5367
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    463
    +0.15
    0.7%
    685
    +0.11
    0.5%
    712
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.15
    -0.01
    141
    +0.11
    0.01
    189
    +0.10
    0.01
    Negative Logits
    aird
    -0.67
    ftime
    -0.67
    yip
    -0.66
    urally
    -0.66
    uve
    -0.65
    Newsletter
    -0.64
     Gross
    -0.63
    phabet
    -0.63
     Brands
    -0.62
     subtitle
    -0.61
    POSITIVE LOGITS
    */(
    0.69
    TPPStreamerBot
    0.65
    wcsstore
    0.65
    â̳
    0.64
    ãĥ¼ãĥ³
    0.64
    ãĤ·ãĥ£
    0.64
    /_
    0.63
    \/
    0.62
    hell
    0.61
    soDeliveryDate
    0.60
    Activations Density 0.088%

    No Known Activations